data-and-funnel-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for analyzing external funnel data and URLs, which presents a surface for indirect prompt injection.
- Ingestion points: The skill is designed to process user-provided funnel descriptions and URLs as specified in
references/full-guide.md, and dataframes via scripts in theexamples/directory. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands were found in the skill's operational contract.
- Capability inventory: The skill uses Python scripts to perform data analysis and write output files to the workspace (e.g.,
basic_funnel_report.html). - Sanitization: The skill lacks explicit sanitization or filtering logic for external data inputs.
- [EXTERNAL_DOWNLOADS]: The
references/prpm.jsonfile references an external GitHub repository (https://github.com/Tempuss/agent-hub) within its metadata, though no automated download behavior was found in the core logic.
Audit Metadata